Articles
Mostly about building products, healthcare tech, and lessons learned along the way.
Mostly about building products, healthcare tech, and lessons learned along the way.
Older posts from the archive.

Q-LoRA + SFTTrainer + Flash Attention v2 means you can fine-tune a 70B parameter model on 24GB of VRAM. What that looks like end-to-end, what it costs in quality, and when to just use the API instead.

I've made bets that paid off because of timing and bets that paid off because of compounding. Confusing the two is how careers stall.

The prediction was: bigger models win. The reality was: DeepSeek R1 rewrote the rules in January and nothing was the same after that. What 2025 taught us about reasoning, inference-time compute, and the economics of intelligence.

Contractors sell time. Consultants sell results. That distinction is the whole game. How I changed my pricing, positioning, and client selection once it clicked.

Coding agents are the most economically viable AI in production today. The patterns Devin, Cline, Amp, and others converged on, and what they mean for anyone building or using agents seriously.

12 features shipped in a quarter. Zero meaningful metrics moved. AI products aren't software projects. The roadmap is a hypothesis board, not a delivery schedule, and treating it otherwise is expensive.

Chunk-based RAG returns results. Faceted context gives agents peripheral vision: an understanding of the information landscape that lets them navigate rather than just consume. What that looks like in a domain where getting it wrong matters.

Prompt engineering is a symptom, not a skill. The engineers shipping better agents aren't writing better instructions. They're designing better information spaces. Context engineering is the meta-skill no one teaches.

REST APIs were designed for humans calling services through UIs. AI agents are not humans. What breaks when you expose your existing APIs to agents, and what the right architecture looks like.